aloobun commited on
Commit
a57fd30
·
verified ·
1 Parent(s): a8065fe

Delete d-SmolLM2-360M

Browse files
d-SmolLM2-360M/config.json DELETED
@@ -1,32 +0,0 @@
1
- {
2
- "_name_or_path": "HuggingFaceTB/SmolLM2-360M",
3
- "architectures": [
4
- "LlamaForCausalLM"
5
- ],
6
- "attention_bias": false,
7
- "attention_dropout": 0.0,
8
- "bos_token_id": 0,
9
- "eos_token_id": 0,
10
- "head_dim": 64,
11
- "hidden_act": "silu",
12
- "hidden_size": 960,
13
- "initializer_range": 0.02,
14
- "intermediate_size": 2560,
15
- "is_llama_config": true,
16
- "max_position_embeddings": 8192,
17
- "mlp_bias": false,
18
- "model_type": "llama",
19
- "num_attention_heads": 15,
20
- "num_hidden_layers": 32,
21
- "num_key_value_heads": 5,
22
- "pretraining_tp": 1,
23
- "rms_norm_eps": 1e-05,
24
- "rope_interleaved": false,
25
- "rope_scaling": null,
26
- "rope_theta": 100000,
27
- "tie_word_embeddings": true,
28
- "torch_dtype": "bfloat16",
29
- "transformers_version": "4.46.3",
30
- "use_cache": true,
31
- "vocab_size": 49152
32
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d-SmolLM2-360M/generation_config.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 0,
4
- "eos_token_id": 0,
5
- "transformers_version": "4.46.3"
6
- }
 
 
 
 
 
 
 
d-SmolLM2-360M/merges.txt DELETED
The diff for this file is too large to render. See raw diff
 
d-SmolLM2-360M/model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:962f102fbb28821453a7b050f20da510b7f241921740b678fdaa845f6e6988d0
3
- size 723674912
 
 
 
 
d-SmolLM2-360M/special_tokens_map.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "additional_special_tokens": [
3
- "<|endoftext|>",
4
- "<|im_start|>",
5
- "<|im_end|>",
6
- "<repo_name>",
7
- "<reponame>",
8
- "<file_sep>",
9
- "<filename>",
10
- "<gh_stars>",
11
- "<issue_start>",
12
- "<issue_comment>",
13
- "<issue_closed>",
14
- "<jupyter_start>",
15
- "<jupyter_text>",
16
- "<jupyter_code>",
17
- "<jupyter_output>",
18
- "<jupyter_script>",
19
- "<empty_output>"
20
- ],
21
- "bos_token": {
22
- "content": "<|endoftext|>",
23
- "lstrip": false,
24
- "normalized": false,
25
- "rstrip": false,
26
- "single_word": false
27
- },
28
- "eos_token": {
29
- "content": "<|endoftext|>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false
34
- },
35
- "pad_token": "<|endoftext|>",
36
- "unk_token": {
37
- "content": "<|endoftext|>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false
42
- }
43
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d-SmolLM2-360M/tokenizer.json DELETED
The diff for this file is too large to render. See raw diff
 
d-SmolLM2-360M/tokenizer_config.json DELETED
@@ -1,168 +0,0 @@
1
- {
2
- "add_prefix_space": false,
3
- "added_tokens_decoder": {
4
- "0": {
5
- "content": "<|endoftext|>",
6
- "lstrip": false,
7
- "normalized": false,
8
- "rstrip": false,
9
- "single_word": false,
10
- "special": true
11
- },
12
- "1": {
13
- "content": "<|im_start|>",
14
- "lstrip": false,
15
- "normalized": false,
16
- "rstrip": false,
17
- "single_word": false,
18
- "special": true
19
- },
20
- "2": {
21
- "content": "<|im_end|>",
22
- "lstrip": false,
23
- "normalized": false,
24
- "rstrip": false,
25
- "single_word": false,
26
- "special": true
27
- },
28
- "3": {
29
- "content": "<repo_name>",
30
- "lstrip": false,
31
- "normalized": false,
32
- "rstrip": false,
33
- "single_word": false,
34
- "special": true
35
- },
36
- "4": {
37
- "content": "<reponame>",
38
- "lstrip": false,
39
- "normalized": false,
40
- "rstrip": false,
41
- "single_word": false,
42
- "special": true
43
- },
44
- "5": {
45
- "content": "<file_sep>",
46
- "lstrip": false,
47
- "normalized": false,
48
- "rstrip": false,
49
- "single_word": false,
50
- "special": true
51
- },
52
- "6": {
53
- "content": "<filename>",
54
- "lstrip": false,
55
- "normalized": false,
56
- "rstrip": false,
57
- "single_word": false,
58
- "special": true
59
- },
60
- "7": {
61
- "content": "<gh_stars>",
62
- "lstrip": false,
63
- "normalized": false,
64
- "rstrip": false,
65
- "single_word": false,
66
- "special": true
67
- },
68
- "8": {
69
- "content": "<issue_start>",
70
- "lstrip": false,
71
- "normalized": false,
72
- "rstrip": false,
73
- "single_word": false,
74
- "special": true
75
- },
76
- "9": {
77
- "content": "<issue_comment>",
78
- "lstrip": false,
79
- "normalized": false,
80
- "rstrip": false,
81
- "single_word": false,
82
- "special": true
83
- },
84
- "10": {
85
- "content": "<issue_closed>",
86
- "lstrip": false,
87
- "normalized": false,
88
- "rstrip": false,
89
- "single_word": false,
90
- "special": true
91
- },
92
- "11": {
93
- "content": "<jupyter_start>",
94
- "lstrip": false,
95
- "normalized": false,
96
- "rstrip": false,
97
- "single_word": false,
98
- "special": true
99
- },
100
- "12": {
101
- "content": "<jupyter_text>",
102
- "lstrip": false,
103
- "normalized": false,
104
- "rstrip": false,
105
- "single_word": false,
106
- "special": true
107
- },
108
- "13": {
109
- "content": "<jupyter_code>",
110
- "lstrip": false,
111
- "normalized": false,
112
- "rstrip": false,
113
- "single_word": false,
114
- "special": true
115
- },
116
- "14": {
117
- "content": "<jupyter_output>",
118
- "lstrip": false,
119
- "normalized": false,
120
- "rstrip": false,
121
- "single_word": false,
122
- "special": true
123
- },
124
- "15": {
125
- "content": "<jupyter_script>",
126
- "lstrip": false,
127
- "normalized": false,
128
- "rstrip": false,
129
- "single_word": false,
130
- "special": true
131
- },
132
- "16": {
133
- "content": "<empty_output>",
134
- "lstrip": false,
135
- "normalized": false,
136
- "rstrip": false,
137
- "single_word": false,
138
- "special": true
139
- }
140
- },
141
- "additional_special_tokens": [
142
- "<|endoftext|>",
143
- "<|im_start|>",
144
- "<|im_end|>",
145
- "<repo_name>",
146
- "<reponame>",
147
- "<file_sep>",
148
- "<filename>",
149
- "<gh_stars>",
150
- "<issue_start>",
151
- "<issue_comment>",
152
- "<issue_closed>",
153
- "<jupyter_start>",
154
- "<jupyter_text>",
155
- "<jupyter_code>",
156
- "<jupyter_output>",
157
- "<jupyter_script>",
158
- "<empty_output>"
159
- ],
160
- "bos_token": "<|endoftext|>",
161
- "clean_up_tokenization_spaces": false,
162
- "eos_token": "<|endoftext|>",
163
- "model_max_length": 8192,
164
- "pad_token": "<|endoftext|>",
165
- "tokenizer_class": "GPT2Tokenizer",
166
- "unk_token": "<|endoftext|>",
167
- "vocab_size": 49152
168
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
d-SmolLM2-360M/vocab.json DELETED
The diff for this file is too large to render. See raw diff